VUCOMISS (XMM, M32) - Port Usage

With blocking instructions for ports {'2', '3'}:

Code:

   0:	0f 72 f0 02          	pslld  mm0,0x2
   4:	0f 72 f1 02          	pslld  mm1,0x2
   8:	0f 72 f2 02          	pslld  mm2,0x2
   c:	0f 72 f3 02          	pslld  mm3,0x2
  10:	0f 72 f4 02          	pslld  mm4,0x2
  14:	0f 72 f5 02          	pslld  mm5,0x2
  18:	0f 72 f6 02          	pslld  mm6,0x2
  1c:	0f 72 f7 02          	pslld  mm7,0x2
  20:	0f 72 f0 02          	pslld  mm0,0x2
  24:	0f 72 f1 02          	pslld  mm1,0x2
  28:	c4 c1 78 2e 06       	vucomiss xmm0,DWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 4.7
- APERF: 5.57
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 5.55
- FpuPipeAssignment.Total3: 5.45
- FpuPipeAssignment.Total4: 0.02
- FpuPipeAssignment.Total5: 0.98

⇨ One μop that can only use ports {'2', '3'}

With blocking instructions for ports {'4', '5'}:

Code:

   0:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
   5:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
   a:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
   f:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  14:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  19:	c5 f9 7e cb          	vmovd  ebx,xmm1
  1d:	c5 f9 7e c9          	vmovd  ecx,xmm1
  21:	c5 f9 7e ca          	vmovd  edx,xmm1
  25:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  2a:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  2f:	c4 c1 78 2e 06       	vucomiss xmm0,DWORD PTR [r14]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM1, XMM1, XMM1;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14]

Show nanoBench command
Results:
- MPERF: 8.77
- APERF: 10.06
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.1
- FpuPipeAssignment.Total3: 0.9
- FpuPipeAssignment.Total4: 5.53
- FpuPipeAssignment.Total5: 5.47

⇨ One μop that can only use ports {'4', '5'}

With an indexed addressing mode

With blocking instructions for ports {'2', '3'}:

Code:

   0:	0f 72 f0 02          	pslld  mm0,0x2
   4:	0f 72 f1 02          	pslld  mm1,0x2
   8:	0f 72 f2 02          	pslld  mm2,0x2
   c:	0f 72 f3 02          	pslld  mm3,0x2
  10:	0f 72 f4 02          	pslld  mm4,0x2
  14:	0f 72 f5 02          	pslld  mm5,0x2
  18:	0f 72 f6 02          	pslld  mm6,0x2
  1c:	0f 72 f7 02          	pslld  mm7,0x2
  20:	0f 72 f0 02          	pslld  mm0,0x2
  24:	0f 72 f1 02          	pslld  mm1,0x2
  28:	c4 81 78 2e 04 2e    	vucomiss xmm0,DWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
PXOR MM0, MM0;
PXOR MM1, MM1;
PXOR MM2, MM2;
PXOR MM3, MM3;
PXOR MM4, MM4;
PXOR MM5, MM5;
PXOR MM6, MM6;
PXOR MM7, MM7;
VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 4.86
- APERF: 5.57
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 5.55
- FpuPipeAssignment.Total3: 5.45
- FpuPipeAssignment.Total4: 0.02
- FpuPipeAssignment.Total5: 0.98

⇨ One μop that can only use ports {'2', '3'}

With blocking instructions for ports {'4', '5'}:

Code:

   0:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
   5:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
   a:	c4 c1 79 7e ca       	vmovd  r10d,xmm1
   f:	c4 c1 79 7e cb       	vmovd  r11d,xmm1
  14:	c4 c1 79 7e cc       	vmovd  r12d,xmm1
  19:	c5 f9 7e cb          	vmovd  ebx,xmm1
  1d:	c5 f9 7e c9          	vmovd  ecx,xmm1
  21:	c5 f9 7e ca          	vmovd  edx,xmm1
  25:	c4 c1 79 7e c8       	vmovd  r8d,xmm1
  2a:	c4 c1 79 7e c9       	vmovd  r9d,xmm1
  2f:	c4 81 78 2e 04 2e    	vucomiss xmm0,DWORD PTR [r14+r13*1]

Init:

MOV R15, 10000;
L: VADDPS YMM0, YMM1, YMM1;
VADDPS YMM0, YMM1, YMM1;
DEC R15;
JNZ L;
VZEROALL;
VXORPS XMM1, XMM1, XMM1;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
VMOVUPD XMM0, [R14];
XOR R13, R13

Show nanoBench command
Results:
- MPERF: 8.7
- APERF: 10.05
- FpuPipeAssignment.Total0: 0.0
- FpuPipeAssignment.Total1: 0.0
- FpuPipeAssignment.Total2: 0.94
- FpuPipeAssignment.Total3: 0.06
- FpuPipeAssignment.Total4: 5.47
- FpuPipeAssignment.Total5: 5.53

⇨ One μop that can only use ports {'4', '5'}